Portfolio

Table of contents

• R / RStudio
  • ggplot2
  • plotly - Interactive Graphs
• Python
  • Pandas, Numpy, Altair

R / RStudio

Librares

library(mosaic)
library(tidyverse)
library(plotly)
library(reticulate)

ggplot2

Data manipulation + boxplot code

food <- read_csv("data/food.csv")

food1 <- food %>% 
  select(c(GPA, father_education, mother_education))

food2 <- food1 %>% 
mutate(
parent_education = case_when(
    mother_education == 1 & father_education == 1 ~
    "BHSD",
    mother_education %in% c(1,2) & father_education == 2 | 
    mother_education == 2 & father_education == 1 ~ 
    "1HS",
    mother_education %in% c(1,2,3) & father_education == 3 |
    mother_education == 3 & father_education %in% c(1,2) ~
    "1SC",
    mother_education %in% c(1,2,3,4) & father_education == 4 |
    mother_education == 4 & father_education %in% c(1,2,3) ~
    "1BD",
    mother_education %in% c(1,2,3,4) & father_education == 5 |
    mother_education == 5 & father_education %in% c(1,2,3,4) ~
    "1GD",
    mother_education == 5 & father_education == 5 ~
    "BGD"
),
GPA = as.numeric(GPA)
) %>% 
na.omit()

food2 <- food2 %>% 
  mutate(
    parent_education = fct_relevel(parent_education,
                                        "BHSD", "1HS", "1SC",
                                        "1BD", "1GD", "BGD")
  )

ggplot(food2, aes(x=parent_education, y=GPA)) +
  geom_boxplot(fill=c('cyan3','deepskyblue','deepskyblue1','deepskyblue2','deepskyblue3','deepskyblue4')) +
  geom_jitter(color="black", size=1, alpha=0.9, width= 0.25) +
  labs(title= "How do Parent's Education Levels Effect College Student's GPAs?",
       x= "Parent's Education Levels") +
  theme_light()

• Both High school Dropouts (BHSD)

• At least one high school graduate (1HS)

• At least one did some college (1SC)

• At least one bachelors degree (1BD)

• At least one graduate degree (1GD)

• Both graduate degrees (BGD)

To see full analysis this chart was used in: College GPA vs Parental Education

plotly - Interactive Graphs

plotly code

Rent <- read_csv("data/rent.csv")

wRent <- Rent %>% 
  filter(Gender == 'F' & Price < 1000) %>% 
  mutate(
    MilesToCampus = round(MilesToCampus, 2)
  )

plot_ly(wRent,
        x= ~MilesToCampus,
        y= ~Capacity,
        color=~Price,
        colors=c("hotpink","hotpink4"), 
        size= ~Price,
        text= ~paste(Apartment, "\n$", Price)) %>% 
  layout(title= "Womens BYU-I Approved Housing\nUnder $1000 per Semester",
         xaxis=list(title="Miles to the Center of Campus"),
         yaxis=list(title="Maximum Housing Capacity"))

To see full analysis this chart was used in: Housing Analysis for Stephanie

Python

Libraries

import pandas as pd
import numpy as np
import altair as alt

from IPython.display import Markdown
from IPython.display import display
from tabulate import tabulate

Pandas, Numpy, Altair

Code

names = pd.read_csv("https://github.com/byuidatascience/data4names/raw/master/data-raw/names_year/names_year.csv")

christian_names = names.query("name == ['Mary', 'Martha', 'Peter', 'Paul']")
christian_chart = alt.Chart(christian_names,
                            title = alt.Title(
                           "People Born Each Year",
                           subtitle= "with the names 'Martha', 'Mary', 'Paul', and 'Peter'"
                            )
).encode(
    x = alt.X('year',
              title = "Year")
            .axis(format = "d"),
    y = alt.Y('Total'),
    color = 'name'
)

christian_chart.mark_line()

Code

flights = pd.read_json("https://github.com/byuidatascience/data4missing/raw/master/data-raw/flights_missing/flights_missing.json")

# Gets rid of characters and just leaves numbers
flights['num_of_delays_carrier'] = (
    flights['num_of_delays_carrier'].str.replace(r'\D', '', regex=True)
)
# Replaces blank strings, -999, and "n/a" with the actual NaN value
flights = (flights
    .replace(["", -999, "n/a"], np.nan)
    .replace(["Febuary"], "February")
)
# Fills NaN values in num_of_delays_late_aircraft with the mean of the column
mean_late_air = flights.num_of_delays_late_aircraft.mean()
flights.num_of_delays_late_aircraft.fillna(mean_late_air, inplace=True)
# Fills NaN values with the month before them
flights.month.ffill(inplace=True)

totals = (flights
 .groupby("airport_code")
 .agg(
     total_minutes_delayed = 
     ("minutes_delayed_total", np.sum),
     total_delays = 
     ("num_of_delays_total", np.sum),
     total_flights = 
     ("num_of_flights_total", np.sum),
).assign(
    total_hrs_delayed = lambda df: df.total_minutes_delayed / 60,
    ave_hrs_delayed = lambda df: df.total_hrs_delayed / df.total_delays,
    proportion_delayed = lambda df: df.total_delays / df.total_flights,
    delay_rating = lambda df: df.proportion_delayed * df.ave_hrs_delayed
).sort_values('delay_rating', ascending=False)
.reset_index()
)

best_airport = alt.Chart(totals,
                         title= alt.Title(
                             "Airports Rated by Delay",
                             subtitle= "The higher the rating, the worse airport")).encode(
    x = alt.X('delay_rating:Q', title="Delay Rating"),
    y= alt.Y('airport_code:N', title="Airport Code", sort="-x"),
    color=alt.Color('airport_code:N', legend=None).scale(scheme="tealblues")
).mark_bar()
best_airport